Apple M1 Microarchitecture Research by Dougall Johnson

Firestorm: Overview | Base Instructions | SIMD and FP Instructions
Icestorm:  Overview | Base Instructions | SIMD and FP Instructions

FCVTNU (vector, 4S)

Test 1: uops

Code:

  fcvtnu v0.4s, v0.4s
  movi v0.16b, 1
  movi v1.16b, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)03091e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op fp/simd (7e)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
1004303724008225472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037240010325472510001000100039816013022303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037240012425472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723007825472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtnu v0.4s, v0.4s
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03191e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037233000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000710116112963300100001003003830038300383003830038
102043003723301201382954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000710116112963300100001003003830038300383003830038
1020430037232000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000710116112963300100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000710116112963300100001003003830038300383003830038
10204300372320007262954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000710116012963300100001003003830038300383003830038
1020430037232000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000710116112963300100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000710116112963300100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000710116112963300100001003003830038300383003830038
1020430037232000892954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000710116112963300100001003003830038300383003830038
1020430037232000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000710116112963300100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0318191e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8acc2branch mispredict (cb)cdcfd5d6d9ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003723300186129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000064021602229629010000103003830038300383003830038
10024300372330006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000104000064021602229629010000103003830038300383003830038
10024300372330006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000064021602229629010000103003830038300383003830038
10024300372250006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000064021602229629010000103003830038300383003830038
10024300372250006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000064021602229629010000103003830038300383003830038
10024300372250006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000064021602229629010000103003830038300383003830038
10024300372250006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000064021602229629010000103003830038300383003830038
10024300372250006129547251001010100001010000504279864030018300373003728286328767103122010000201000030037300371110021109101010000100407500064021602229629310000103003830038300383003830038
10024300372250006129547251001010100001010000504277160030018300373017928286328767100102010000201000030037300371110021109101010000100000064021602229629010000103003830038300383003830038
10024300372250006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000064021602229629010000103003830038300383003830085

Test 3: throughput

Count: 8

Code:

  fcvtnu v0.4s, v8.4s
  fcvtnu v1.4s, v8.4s
  fcvtnu v2.4s, v8.4s
  fcvtnu v3.4s, v8.4s
  fcvtnu v4.4s, v8.4s
  fcvtnu v5.4s, v8.4s
  fcvtnu v6.4s, v8.4s
  fcvtnu v7.4s, v8.4s
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)030b1e3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696b6d6edispatch stall (70)72scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915501258258010810080008100800205006401321200200200392003999770699908012020080032200800322003920039118020110099100100800001000011151181160020036800001002004020040200402004020040
802042003915503330258010810080008100800205006401320200200200392003999770699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391550030258010810080008100800205006401321200200200392003999770699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391550030258010810080008100800205006401320200200200392003999770699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391550030258010810080008100800205006401320200200200392003999770699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
802042003915500695258010810080008100800205006401320200200200392003999770699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391550030258010810080008100800205006401320200200200392003999770699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
802042003915501530258010810080008100800205006401321200200200392003999770699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391550030258010810080008100800205006401320200200200392003999770699908012020080032200800322003920039118020110099100100800001001011151180160020036800001002004020040200402004020040
80204200391560030258010810080008100800205006401320200200200392003999770699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)030718191e1f3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)72scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accdcfd0d5d6ddinst fetch restart (de)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015500000692580010108000010800005064000002002020039200399996031001980010208000020800002003920039118002110910108000010000502003163320036080000102004020040200402004020040
800242003915600000402580010108000010800005064000012002020039200399996031001980010208000020800002003920039118002110910108000010000502003163320036080000102004020040200402004020040
800242003915500000402580010108000010800005064000002002020039200399996031001980010208000020800002003920039118002110910108000010000502003164320036080000102004020040200402004020040
800242003915500000402580010108000010800005064000012002020039200399996031001980010208000020800002003920039118002110910108000010000502003163220036080000102004020040200402004020040
800242003915500000402580010108000010800005064000002002020039200399996031001980010208000020800002003920039118002110910108000010000502002162320036080000102004020040200402004020040
800242003915500000402580010108000010800005064000012002020039200399996031001980010208000020800002003920039118002110910108000010030502003163220036080000102004020040200402004020040
8002420039155000150402580010108000010800005064000012002020039200399996031001980010208000020800002003920039118002110910108000010000502003163220036080000102004020040201122004020040
800242003915500000402580010108000010800005064000002002020039200399996031001980010208000020800002003920039118002110910108000010000502003163320036080000102004020040200402004020040
8002420039155000210402580010108000010800005064000002002020039200399996031001980010208000020800002003920039118002110910108000010000502003163320036080000102004020040200402004020040
800242003915600000402580010108000010800005064000002002020039200399996031001980010208000020800002003920039118002110910108000010000502002163220036080000102004020040200402004020040